Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    players, capabilities, states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     бед
    0.42
     роль
    0.42
     เนาะ
    0.41
     ਪਰ
    0.41
     Vielleicht
    0.41
     kinematic
    0.40
    ственно
    0.40
     стати
    0.40
     사회
    0.40
     Тор
    0.40
    POSITIVE LOGITS
    plane
    0.44
     náklady
    0.41
     fanfare
    0.41
    joner
    0.40
    运营
    0.39
    ngl
    0.39
     Chiron
    0.39
    ഫ
    0.39
     inaug
    0.38
     MPM
    0.38
    Act Density 0.001%

    No Known Activations